PixelBoost 8 – Pixel Quality with 8X Highlights Boosting Enhancement
Sheetal S. Patil1, Avinash M. Pawar2, Nilofar Mulla3, Jotiram Krishna Deshmukh4, Avinash M. Deshmukh5, Suresh Kumar Ray6
1Dr. Sheetal S. Patil, Department of Computer Science & Business Systems, Bharati Vidyapeeth (Deemed to be University) College of Engineering, Pune (Maharashtra), India.
2Dr. Avinash M. Pawar, Department of Mechanical Engineering, Bharati Vidyapeeth’s College of Engineering for Women, Pune (Maharashtra), India.
3Dr. Nilofar Mulla, Department of Information Technology, Bharati Vidyapeeth’s College of Engineering for Women, Pune (Maharashtra), India.
4Dr. Jotiram Krishna Deshmukh, Department of Instrumentation Engineering, Bharati Vidyapeeth College of Engineering, Navi Mumbai (Maharashtra), India.
5Dr. Avinash M. Deshmukh, Basic Science and Engineering Department, SCTR’s Pune Institute of Computer Technology, Pune (Maharashtra), India.
6Dr. Suresh Kumar Ray, Bharati Vidyapeeth (Deemed to be University) College of Nursing, Sangli (Maharashtra), India.
Manuscript received on 07 July 2026 | First Revised Manuscript received on 01 August 2026 | Second Manuscript Accepted on 08 August 2026 | Manuscript Accepted on 15 August 2026 | Manuscript published on 30 August 2026 | PP: 10-17 | Volume-15 Issue-6, August 2026 | Retrieval Number: 100.1/ijeat.A479816011026 | DOI: 10.35940/ijeat.A4798.15060826
Open Access | Editorial and Publishing Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In recent years, deep learning has become a fundamental technology across a wide array of scientific and industrial fields, largely fuelled by advances in computational capabilities. One area that has experienced substantial progress is face hallucination—the task of improving the resolution of facial images. This process is critical to various computer vision applications, including facial recognition, feature extraction, and identity verification. Recently, deep generative models, particularly Generative Adversarial Networks (GANs), have led the field. Although these models have produced remarkable results, there is still a pressing need to further improve both accuracy and output quality. In order to address these problems, we propose a new GAN-based face hallucination method. This method is primarily based on the Enhanced Super-Resolution Generative Adversarial Network (ESRGAN). We present a personalised adaptation of ESRGAN that employs the VGG16 architecture with a compact pre-trained version. This method balances output image quality and computational efficiency. Experiments show that our approach is effective. The improved model obtains a maximum peak signal-to-noise ratio (PSNR) of 30.30. The Learned Perceptual Image Patch Similarity (LPIPS) score is 0.0817, whereas the Structural Similarity Index Measure (SSIM) is 0.8757. The results surpass many state-of-the-art methods available today. These enhancements have a significant impact and importance.
Keywords: Low Resolutions, Face Hallucinations, ESRGAN Architecture, Super Resolutions.
Scope of the Article: Computer Science and Engineering